检索结果-内蒙古大学图书馆

Drone-Based Public Surveillance Using 3D Point Clouds and Neuro-Fuzzy Classifier

Computers, Materials & Continua 2025年第3期82卷 4759-4776页

作者： Yawar Abbas Aisha Ahmed Alarfaj Ebtisam Abdullah Alabdulqader Asaad Algarni Ahmad Jalal Hui Liu Faculty of Computing and AI Air UniversityIslamabad44000Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Information Technology College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Computer Science and Engineering College of InformaticsKorea UniversitySeoul02841Republic of Korea Cognitive Systems Lab University of BremenBremen28359Germany

Human Activity Recognition(HAR)in drone-captured videos has become popular because of the interest in various fields such as video surveillance,sports analysis,and human-robot ***,recognizing actions from such videos poses the following challenges:variations of human motion,the complexity of backdrops,motion blurs,occlusions,and restricted camera *** research presents a human activity recognition system to address these challenges by working with drones’red-green-blue(RGB)*** first step in the proposed system involves partitioning videos into frames and then using bilateral filtering to improve the quality of object foregrounds while reducing background interference before converting from RGB to grayscale *** YOLO(You Only Look Once)algorithm detects and extracts humans from each frame,obtaining their skeletons for further *** joint angles,displacement and velocity,histogram of oriented gradients(HOG),3D points,and geodesic Distance are *** features are optimized using Quadratic Discriminant Analysis(QDA)and utilized in a Neuro-Fuzzy Classifier(NFC)for activity ***-world evaluations on the Drone-Action,Unmanned Aerial Vehicle(UAV)-Gesture,and Okutama-Action datasets substantiate the proposed system’s superiority in accuracy rates over existing *** particular,the system obtains recognition rates of 93%for drone action,97%for UAV gestures,and 81%for Okutama-action,demonstrating the system’s reliability and ability to learn human activity from drone videos.

关键词： Activity recognition geodesic distance pattern recognition neuro fuzzy classifier

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Trading Model for Stock Price Forecasting Integrating Forester with Golden Ratio Strategy 12

Algorithmic Trading Model for Stock Price Forecasting Integr...

引用

12th IEEE Region 10 Humanitarian Technology Conference, R10-HTC 2024

作者： Govindan, Niranjana Baskaran, Bharathi Azizan, Azizul Yakub, Fitri Dhamanti, Inge Dhaya, C. SRMIST Faculty of Engineering & Technology Department of Computing Technologies Kattankulathur Chennai India Faculty of Intelligence Kuala Lumpur Malaysia Malaysia-Japan International Institute of Technology UTM Electronic System Engineering Department Kuala Lumpur Malaysia Universitas Airlangga Faculty of Public Health Department of Health Policy and Administration Surabaya Indonesia Adhiparasakthi Engineering College Department of Computer Science and Technology Melmaruvathur India

ISBN: (纸本)9798350340204

Algorithmic trading has emerged as a powerful tool for making data-driven trading decisions in financial markets. In this paper, we present an innovative algorithmic trading model for stock price forecasting that integrates forest-based machine learning algorithms with the Golden Ratio strategy. Our proposed approach aims to leverage the predictive power of machine learning while incorporating insights from technical analysis to enhance trading performance and profitability. The methodology involves data collection and preprocessing, feature engineering, model development, and performance evaluation. Historical stock price data, financial indicators, and sentiment analysis data are gathered and pre-processed to ensure data quality. Feature engineering techniques are applied to extract relevant features, and forest-based machine learning algorithms are trained on the data to forecast stock prices. The Golden Ratio strategy is integrated into the trading model to identify the entry point and exit point. Empirical validation and performance evaluation demonstrate the effectiveness and robustness of the proposed approach. Through back testing and simulation-based testing, we evaluate the model's accuracy, profitability, and risk-adjusted returns. Our findings contribute to the advancement of algorithmic trading research and practice, offering insights into the potential benefits of combining machine learning algorithms with established trading strategies. The proposed hybrid model incorporates Golden Ratio Strategy, integrating Random Forest (RF). The results of the proposed random forest with Golden Ratio Strategy are compared with the results of individual model. This comparison helps in proving the efficiency of the proposed model. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Novel Image Encryption System 8

Design and Implementation of a Novel Image Encryption System

引用

8th International Conference on Intelligent computing and Signal Processing, ICSP 2023

作者： Chen, Enhao Shu, Yingying Chen, Zongwei Wang, Xinru Nie, Xin Gao, Shuyi Liu, Zongrui Zou, Yijia Harbin Institute of Technology Faculty of Computing Harbin China Harbin Institute of Technology Faculty of Materials Science and Engineering Harbin China Harbin Institute of Technology Faculty of Science Harbin China Harbin Institute of Technology Faculty of New Energy Harbin China Harbin Institute of Technology School of Economics and Management Harbin China

ISBN: (纸本)9798350302455

The field of image encryption is studied to encrypt and hide the image effectively, and the most critical thing is whether the image can be restored without any loss of details or distortion. Classical cryptography provides good encryption and decryption algorithms for one-dimensional data streams, encrypting plaintext data into ciphertext data for the purpose of confidentiality. Although we can consider the image data as a one-dimensional data stream and use traditional encryption algorithms for encryption, these algorithms often ignore some special properties of digital images such as two-dimensional self-similarity, large data volume, etc. Moreover, traditional encryption algorithms can hardly meet the real-time requirements in network transmission. Therefore, we improve the traditional encryption techniques for digital images, and process the images by means of Arnold matrix transform, two-dimensional logistic chaos mapping, and DWT and DCT transforms, and experimentally verify that the method has faster and lower loss degree, which confirms the feasibility of its application in the field of professional encryption. © 2023 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Enhanced Sensing for Automotive mmWave Radar: Super-Resolution Range and Angle Estimation With Coherent Extension and Advanced IAA

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Wu, Zhenyu Ma, Xuxu Chang, Fei Li, Chuandong Luo, Zhen Leung, Man-Fai Southwest University College of Electronic and Information Engineering Chongqing400715 China Anglia Ruskin University School of Computing and Information Science Faculty of Science and Engineering Cambridge United Kingdom

This article delves into the super-resolution problem of range and angle for millimeter wave (mmWave) frequency-modulated continuous wave radar. First, a modified diagonal loading (MDL) is proposed for range estimation in practical scenarios to improve the convergence of the iterative adaptive approach (IAA). This loading term can be flexibly adjusted according to the actual noise level, and it has the potential to surpass the existing adaptive diagonal loading IAA under low signal-to-noise ratio. Second, the range estimation results are used for signal enhancement. A coherent extension technique is adopted to address the phase discontinuity between adjacent chirps, thus enabling the construction of a longer chirp signal. Finally, the extended signal is used to generate a super-resolution range-angle map. Practical and numerical examples demonstrate the feasibility of the above methodology. © 2025 IEEE. All rights reserved.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Maternal Health Risk Classification - A Comparison between Algorithm Decision Tree and k-Nearest Neighbor (kNN)

Maternal Health Risk Classification - A Comparison between A...

引用

2023 International Conference on Sustainable Emerging Innovations in engineering and Technology, ICSEIET 2023

作者： Fatmawati, Maylia Novita, Mega Saputro, Nugroho Dwi Chauhan, Alok Singh Nada, Noora Qotrun Sinha, Amit Herlambang, Bambang Agus Gupta, Shruti Universitas Pgri Semarang Faculty of Engineering and Informatics Department of Informatics Semarang Indonesia Universitas Pgri Semarang Postgraduate Program of Science Education Semarang Indonesia School of Computing Science & Engineering Galgotias University Greater Noida India ABES Engineering College Department of Computer Science & Engineering Uttar Pradesh Ghaziabad201009 India

ISBN: (纸本)9798350329186

Maternal health is a critical concern, particularly for individuals who are pregnant and will shape the future generations. However, not all expectant mothers receive tailored attention and care for their unique health needs. Consequently, many mothers face high levels of health risks during pregnancy, highlighting the importance of classifying maternal health risks. Classification can help identify influential factors affecting maternal health and predict risk levels for individual mothers. In the field of data mining, various classification methods exist for analyzing complex datasets. This study focuses on two widely used algorithms: decision tree and k-Nearest Neighbor (kNN). By employing these algorithms, we aim to classify a dataset comprising 1,014 records of maternal health risk levels. Through cross-validation and T-tests, we rigorously evaluate the performance of the decision tree and kNN algorithms in this context. Our findings indicate that the kNN algorithm is more suitable for classifying maternal health risks, achieving a significantly higher accuracy of 71.50% compared to the decision tree algorithm's accuracy of 70.71%. This result establishes the superiority of the kNN algorithm in accurately classifying maternal health risks. These findings have implications for developing targeted interventions and tailored healthcare strategies to mitigate identified risks. © 2023 IEEE.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

Fully Automated WSI with CNN Model for Breast Cancer Prediction using Deep Learning 3

Fully Automated WSI with CNN Model for Breast Cancer Predict...

引用

3rd International Conference on Ubiquitous computing and Intelligent Information Systems, ICUIS 2023

作者： Rama, P. Angayarkanni, V. Vidhyalakshmi, M.K. Karuppiah, A. Babu Premalatha, J. College of Engineering and Technology Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Computing Technologies TN Kattankulathur603203 India Srm Institute of Engineering and Technology Department of Electronics and Communication Engineering Tiruchirapalli India Dhanalakshmi Srinivasan Arts and Science College Ecr Mamallapuram Chennai India

ISBN: (纸本)9798350306989

Deep Learning is used for predicting a large volume of data sets in the medical field particularly for breast cancer prediction and diagnosis. The most effective and broadly applied model for detecting breast cancer is the Conventional Neural Network (CNN) among the various deep learning algorithms available. The existing CNN models are lacking in the analysis of a fully labeled Whole Set Image (WSI) data set. The proposed Fully Automate WSI with the CNN model will analyze the whole slide images and patch the input image for improving the accuracy. Then CNN model will get input from patched images and creates classified data for predicting breast cancer. The scikit-learn deep learning framework with Python is used to analyze the result and build a generalized tissue classifier, the WSI data set should include tissues generated under numerous different preparation circumstances. The proposed model experimental results show promising WSI patch values, accuracy, precision, recall, and F1 score of the breast cancer tissues which are used for diagnosis purposes. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Fortifying Database Security: Integrating Advanced Honeypot Technology for Resilient SQL Injection Defense

Fortifying Database Security: Integrating Advanced Honeypot ...

引用

2024 International Conference on Communication, Computer sciences and engineering, IC3SE 2024

作者： Kumaran, U. Swetha, Thammisetty Reddy, G. S. N. Santhosh Ala, Harini Nagarajan, Senthil Murugan Umah, B. Amrita School Of Computing Department Of Computer Science & Engineering Amrita Vishwa Vidyapeetham Bengaluru India Andhra Pradesh Madanapalle India Amrita School Of Engineering Amrita Vishwa Vidyapeetham Department Of Electronics And Communication Engineering Karnataka Bengaluru India University Of Luxembourg Department Of Mathematics Faculty Of Science Technology And Medicine L-4365 Luxembourg Amrita School Of Engineering Amrita Vishwa Vidyapeetham Department Of Computer Science & Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350366846

The dynamic nature of cyber threats necessitates the development of novel approaches to strengthen database system security. The novel method for fortifying defenses against SQL injection attacks - a pervasive and ongoing danger in the field of cybersecurity - is presented in this study. The suggested methodology creates a strong and adaptable defense mechanism by seamlessly integrating cutting-edge honeypot technology with current SQL injection mitigation techniques. Our approach, which we have named HoneySQLGuard, uses carefully con- structed honeypot tables inside the database system. These tables serve as sly bait, drawing potential attackers' attention away from genuine data and toward themselves. By utilizing the most recent developments in technology, Honey SQL Guard surpasses the limitations of conventional signature-based detection techniques and is able to adjust to changing attack strategies via anomaly and machine learning. The honeypot tables are cleverly incorporated within the database architecture, making them invisible to an outside observer when compared to real tables. The technology immediately recognizes and isolates unusual behavior suggestive of SQL injection attempts by closely monitoring and analyzing query patterns. Furthermore, HoneySQLGuard has real-time reporting and alerting functions that guarantee an early reaction to any possible intrusions. Extensive testing is conducted to validate the effectiveness of the proposed solution, which shows it can dramatically lower the success rate of SQL injection attacks while keeping false-positive rates low. This study advances the subject by providing a thorough and flexible method for fortifying databases against SQL injection attacks, in line with the industry's increasing demand for robust cybersecurity defenses. © 2024 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Medical Image Diagnosis with Convolutional Neural Networks 2

Enhancing Medical Image Diagnosis with Convolutional Neural ...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Mahadevan, K. Pushparani, S. SashiRekha, K. Sivagami, V.M. Usharani, R. Department of Computer Science and Engineering CARE College of Engineering Tamil Nadu Trichy India Department of Computer Science and Engineering Meenakshi College of Engineering Tamil Nadu Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of Information Technology Sri Venkateswara College of Engineering Tamil Nadu Chennai India Department of Computational Intelligence School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (纸本)9798350383867

This paper is a comparative analysis of medical image diagnosis algorithms with Convolutional Neural Networks (CNNs) and other methods;such as Support Vector Machine (SVM), Random Forest, and k-nearest Neighbors (k-NN) The study performs evaluations on datasets with multimodalities like medical images and diagnostic and various imaging modalities. Results shows that CNNs have the upper hand over traditional, static algorithms across several metrics that assesses the performance of the system such as accuracy, precision, recall, and F1. In particular, CNN precision was 90.5% while the recall was 93.7%, and the accuracy was 92.1% as well as F1-score 92.0%. In addition, the high area under the Receiver Operating Characteristic curve (AUC-ROC) of over 0.95 for the CNN also signed for its excellent discriminatory power. These outcomes only exemplify CNN usefulness in the diagnostic area because it is an exact and accurate method for analyzing medical images. Although the nets CNNs are deployed in clinical cases may help address concerns regarding interpretability, compliance with regulations, and ethical opinions, such issues still exist and require further exploration. Overall, this research takes the first steps in directing algorithmic approach towards medical diagnosis and show the feasibility in deployment of CNNs as inseparable pieces of equipment in modern healthcare. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Extended Kalman Filter Algorithm to Detect False Data Injection in Wireless Sensor Network 2

Extended Kalman Filter Algorithm to Detect False Data Inject...

引用

2nd International Conference on Augmented Intelligence and Sustainable Systems, ICAISS 2023

作者： Babuji, R. Ganesan, J. Jeya Lekha, D. Karthikeyan, M. Kalai Selvi, D.M. Rmk Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Sri Sairam Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Rmk College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Srm Institute of Science and Technology School of Computing Faculty of Engineering and Technology Department of Computing Technologies Tamil Nadu Chennai India R.M.D. Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350325799

Wireless Sensor Networks (WSN) contains spatially distributed sensor nodes that collaborate with each other. However, the WSN is susceptible since the wireless medium is unpredictable. Several conventional approaches are used to distinguish the abnormal in the WSN, and all have difficulties. An Extended Kalman Filter Algorithm (EKFA) to detect false inject data in WSN is proposed in this paper. It addresses two issues such as abnormality recognition and obstacle detection. It also distinguishes false insert data. Particularly, it observes neighbors' behaviors and then applying EKFA to forecast their future states. The node behavior is observed by incorporating abnormal node examination and system examination elements. The Path Optimization Method (POM) is a shortest route that is used to discover the obstacle in the WSN. The EKFA mechanism minimizes the forwarder count and delay by applying POM. Simulation results demonstrate that the EKFA approach enhances abnormal node detection and minimizes the false negative ratio. © 2023 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Multimodal Deep Representation Learning for Quantum Cross-Platform Verification

引用

Physical Review Letters 2024年第13期133卷 130601页

作者： Yang Qian Yuxuan Du Zhenliang He Min-Hsiu Hsieh Dacheng Tao School of Computer Science Faculty of Engineering College of Computing and Data Science JD Explore Academy Beijing 101111 China *** Beijing 101111 China Taipei 114699 Taiwan

Cross-platform verification, a critical undertaking in the realm of early-stage quantum computing, endeavors to characterize the similarity of two imperfect quantum devices executing identical algorithms, utilizing minimal measurements. While the random measurement approach has been instrumental in this context, the quasiexponential computational demand with increasing qubit count hurdles its feasibility in large-qubit scenarios. To bridge this knowledge gap, here we introduce an innovative multimodal learning approach, recognizing that the formalism of data in this task embodies two distinct modalities: measurement outcomes and classical description of compiled circuits on explored quantum devices, both containing unique information about the quantum devices. Building upon this insight, we devise a multimodal neural network to independently extract knowledge from these modalities, followed by a fusion operation to create a comprehensive data representation. The learned representation can effectively characterize the similarity between the explored quantum devices when executing new quantum algorithms not present in the training data. We evaluate our proposal on platforms featuring diverse noise models, encompassing system sizes up to 50 qubits. The achieved results demonstrate an improvement of 3 orders of magnitude in prediction accuracy compared to the random measurements and offer compelling evidence of the complementary roles played by each modality in cross-platform verification. These findings pave the way for harnessing the power of multimodal learning to overcome challenges in wider quantum system learning tasks.

关键词： Artificial neural networks Deep learning Quantum benchmarking Quantum computation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：